[LoRA] Support Quantized Adapters (#30286)

Signed-off-by: Yu Gong <yu3.gong@gmail.com>
Signed-off-by: wz1qqx <ziqi.wang@novita.ai>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: wz1qqx <55830058+wz1qqx@users.noreply.github.com>
Co-authored-by: wz1qqx <ziqi.wang@novita.ai>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

vllm/lora/ops/triton_ops/__init__.py

@@ -2,6 +2,11 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 
+from vllm.lora.ops.triton_ops.fused_moe_lora_fp8_op import (
+    fused_moe_lora_expand_fp8,
+    fused_moe_lora_fp8,
+    fused_moe_lora_shrink_fp8,
+)
 from vllm.lora.ops.triton_ops.fused_moe_lora_op import (
     fused_moe_lora,
     fused_moe_lora_expand,
@@ -18,4 +23,7 @@ __all__ = [
     "fused_moe_lora",
     "fused_moe_lora_shrink",
     "fused_moe_lora_expand",
+    "fused_moe_lora_fp8",
+    "fused_moe_lora_shrink_fp8",
+    "fused_moe_lora_expand_fp8",
 ]